Character Segmentation of Handwritten Bangla Text by Vertex Characterization of Isothetic Covers

Segmentation of cursive handwriting is one of the most challenging problems in the area of handwritten character recognition. In this paper, we propose a novel approach towards character segmentation in a handwritten document. It is based on the vertex characterization of outer isothetic polygonal covers so that each cover corresponds to a particular word or part of a word. The proposed method has the potential to segment skewed text without deskewing them. Experiment is done on several Bangla handwritings of different individuals. The average success rate is 96.04%. This method can be considered as a significant preprocessing step towards the development of a handwritten Bangla OCR system.